Zone Identification Using Beacon and Sensor Data Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current location-based services face inefficiencies in determining precise zones within venues, as they often require resource-intensive geographic location determination and may not differentiate between specific areas within a venue, such as checkout or parking areas.
Innovation Solution
A system that aggregates beacon and sensor information from mobile devices to dynamically organize samples into classes associated with zones, using a closed feedback loop to improve zone characterization and identification, allowing mobile devices to determine their location within a venue by comparing samples to zone characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If geographic location is determined by comparing wireless signals to a database of known beacons, then venue location can be identified, but processing, memory and device resources are consumed
Solution Approach 1:
The system pre-computes and stores zone characteristics (beacon information and sensor information) for all zones in a venue before runtime. When a mobile device needs location determination, it compares its current samples against these pre-computed characteristics rather than performing full geographic location determination, significantly reducing processing and memory requirements while maintaining accuracy.
Solution Approach 2:
The venue is divided into multiple zones, each with its own characteristic profile. Instead of determining a single geographic location, the system segments the venue space and uses zone-specific characteristics to identify which particular zone the device is in, providing more granular location information with less computational overhead.
2Measurement precision
If geographic location is determined to access venue information, then general venue location is obtained, but precision is insufficient to determine specific sub-portion or region of a venue
Solution Approach 1:
The system adds a new dimension to location determination by incorporating sensor information (lighting, temperature, humidity, noise) alongside beacon information. This multi-dimensional approach creates unique zone profiles that enable precise identification of specific sub-portions within a venue, distinguishing between areas like checkout zones, parking zones, and merchandise zones that would have similar geographic coordinates.
Solution Approach 2:
Each zone within the venue is assigned unique local characteristics (specific beacon patterns and sensor profiles) that reflect its local environment. This allows the system to identify specific sub-portions of the venue by matching the device's observed characteristics against the locally-specific profiles of different zones, achieving high precision without increasing overall system complexity.
3Measurement precision
If static zone characteristics are used for location determination, then system complexity is reduced, but adaptability to changing venue conditions and improved location accuracy is limited
Solution Approach 1:
The system implements a feedback mechanism where mobile devices continuously collect beacon and sensor information samples and transmit them to the server. The server analyzes this feedback data to dynamically update zone characteristics and refine the classification model. This closed-loop feedback enables the system to adapt to venue changes, improve location accuracy over time, and maintain precision even as the physical environment evolves.
Solution Approach 2:
Zone characteristics are transformed from static, pre-defined values to dynamic, evolving profiles that are continuously refined based on actual device observations. The system dynamically adjusts zone boundaries, beacon associations, and sensor thresholds based on accumulated feedback data, enabling adaptability to venue reconfigurations, new beacons, and environmental changes while maintaining high identification accuracy.
Data Source
AI summary
In various embodiments, techniques are provided for determining one or more zones in which mobile devices are presently located and identifying or updating characteristics of on or more zones. Samples that include beacon information and/or sensor information collected by mobile devices are aggregated and dynamically organized into sample classes that are associated with zero, one or more zones. A venue is characterized by a set of zones and associated tags, which may be informed based on samples for the venue, a venue group to which the venue belongs, or all venues. To determine if a mobile device is located in one or more zones, the samples are compared to zone characteristics, and based thereon (and optionally history information) one or more zones are selected having determined likelihoods, and at least a zone having the highest likelihood of the one or more selected zones is returned.